Bar code positioning method in complex scene

A technology of complex scenes and positioning methods, applied in the field of machine vision, can solve problems such as difficulty in achieving real-time performance, large amount of calculation for positioning accuracy, and difficulty in adapting barcode positioning technology to image scenes, so as to reduce the search area and cost, The effect of improving decoding accuracy and good detection effect

Active Publication Date: 2018-12-07
NANJING HUICHUAN IND VISUAL TECH DEV +1
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] The problem to be solved by the present invention is: with the popularization of intelligent mobile devices and the development of image processing technology, image-based barcode recognition technology is widely used, but the current barcode positioning technology is difficult to adapt to complex image scenes; and some The technology with high positioning accuracy has a large amount of calculation, and it is difficult to meet the real-time requirements

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bar code positioning method in complex scene
  • Bar code positioning method in complex scene
  • Bar code positioning method in complex scene

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0044] Such as figure 1 As shown, in the barcode angle calculation part, the present invention first divides the image into several sub-regions, and then uses the Boosted classifier to filter out regions that may contain barcodes according to the histogram of gradient orientation (HOG) features of the sub-regions, and passes the Hough Transform and calculate the rotation angle of the barcode; in the barcode positioning part, the gradient image that can highlight the barcode area is obtained through the gradient difference between the horizontal direction and the vertical direction of the barcode area after rotation, and the horizontal line segment in the detected image is combined with the gradient image , the accurate bounding box of the barcode is obtained by the method of projection. The specific implementation is as follows:

[0045] 1. Barcode angle calculation:

[0046] The barcode is composed of a series of parallel black and white bars with different widths, and has ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Provided is a bar code positioning method in a complex scene. An image is segmented into subareas, a histogram of oriented gradient (HOG) characteristic of each subarea is extracted, and a trained Boosted classifier is used to implement classification; Hough transformation is carried out on the classified subareas to obtain a rotation angle of a bar code, and rotation correction is carried out onthe image; and gradient detection and Hough line segment detection are carried out on the corrected image to obtain an accurate bounding box of the bar code. The method can be used to detect bar codesin different rotation angles and with conditions as distortion, uneven illumination and partial shielding effectively. During detection, prior information and artificial marks are not needed; and theaccurate bounding box of the bar code can be obtained by detection, an accurate bar code area is provided for decoding later, the searching area and cost during decoding are reduced, and the decodingprecision is improved.

Description

technical field [0001] The invention belongs to the technical field of machine vision, relates to a barcode recognition technology, and is a barcode positioning method in complex scenes based on machine learning and Hough transform. Background technique [0002] A barcode is a graphic identifier that arranges a series of black and white bars of different widths according to certain coding rules. It contains most of the information of an item and is most widely used in the logistics and retail industries. The traditional barcode recognition technology is photoelectric barcode recognition technology, which requires special photoelectric scanning, detection and decoding equipment; with the development of image processing technology and the emergence of two-dimensional codes, image-based barcode recognition technology has emerged The wide application of modernized mobile devices has further promoted the development of image barcode recognition technology. [0003] At present, m...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/11G06T7/13G06K9/32G06K7/14
CPCG06K7/146G06T7/11G06T7/13G06V10/243
Inventor 李勃袁宵董蓉周子卿史德飞史春阳查俊
Owner NANJING HUICHUAN IND VISUAL TECH DEV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap